Merge branch 'master' into coverage_enforcing

Author: ChoiByungWook

CHANGELOG.rst

@@ -2,6 +2,11 @@
 CHANGELOG
 =========
 
+1.1.2
+=======
+
+* bug-fix: AmazonEstimators: do not call create bucket if data location is provided
+
 1.1.1
 ========
 

README.rst

@@ -47,7 +47,7 @@ You can install from source by cloning this repository and issuing a pip install
 
     git clone https://github.com/aws/sagemaker-python-sdk.git
     python setup.py sdist
-    pip install dist/sagemaker-1.1.1.tar.gz
+    pip install dist/sagemaker-1.1.2.tar.gz
 
 Supported Python versions
 ~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -1147,7 +1147,7 @@ You need to add them inside the hyperparameters dictionary in the
 -  ``eval_hooks (list)`` A list of `SessionRunHook` hooks to pass during evaluation.
 -  ``eval_delay_secs (int)`` Start evaluating after waiting for this many seconds.
 -  ``continuous_eval_throttle_secs (int)`` Do not re-evaluate unless the last evaluation was started at least this many seconds ago.
--  ``min_eval_frequency (int)`` The minimum number of steps between evaluations. Of course, evaluation does not occur if no new snapshot is available, hence, this is the minimum. If 0, the evaluation will only happen after training. If None, defaults to default is 1000.
+-  ``min_eval_frequency (int)`` The minimum number of steps between evaluations. Of course, evaluation does not occur if no new snapshot is available, hence, this is the minimum. If 0, the evaluation will only happen after training. If None, defaults to 1000.
 -  ``delay_workers_by_global_step (bool)`` if ``True`` delays training workers based on global step instead of time.
 - ``train_steps_per_iteration (int)`` Perform this many (integer) number of train steps for each training-evaluation iteration. With a small value, the model will be evaluated more frequently with more checkpoints saved.
 

doc/conf.py

@@ -18,7 +18,7 @@ def __getattr__(cls, name):
                 'tensorflow.python.framework', 'tensorflow_serving', 'tensorflow_serving.apis']
 sys.modules.update((mod_name, Mock()) for mod_name in MOCK_MODULES)
 
-version = '1.1.1'
+version = '1.1.2'
 project = u'sagemaker'
 
 # Add any Sphinx extension module names here, as strings. They can be extensions

setup.py

@@ -11,7 +11,7 @@ def read(fname):
 
 
 setup(name="sagemaker",
-      version="1.1.1",
+      version="1.1.2",
       description="Open source library for training and deploying models on Amazon SageMaker.",
       packages=find_packages('src'),
       package_dir={'': 'src'},

src/sagemaker/amazon/amazon_estimator.py

@@ -42,8 +42,8 @@ def __init__(self, role, train_instance_count, train_instance_type, data_locatio
         super(AmazonAlgorithmEstimatorBase, self).__init__(role, train_instance_count, train_instance_type,
                                                            **kwargs)
 
-        default_location = "s3://{}/sagemaker-record-sets/".format(self.sagemaker_session.default_bucket())
-        data_location = data_location or default_location
+        data_location = data_location or "s3://{}/sagemaker-record-sets/".format(
+            self.sagemaker_session.default_bucket())
         self.data_location = data_location
 
     def train_image(self):

tests/unit/test_amazon_estimator.py

@@ -88,6 +88,13 @@ def test_data_location_validation(sagemaker_session):
         pca.data_location = "nots3://abcd/efgh"
 
 
+def test_data_location_does_not_call_default_bucket(sagemaker_session):
+    data_location = "s3://my-bucket/path/"
+    pca = PCA(num_components=2, sagemaker_session=sagemaker_session, data_location=data_location, **COMMON_ARGS)
+    assert pca.data_location == data_location
+    assert not sagemaker_session.default_bucket.called
+
+
 def test_pca_hyperparameters(sagemaker_session):
     pca = PCA(num_components=55, algorithm_mode='randomized',
               subtract_mean=True, extra_components=33, sagemaker_session=sagemaker_session,